Sciweavers

208 search results - page 1 / 42
» Detecting Feature Interactions: How Many Components Do We Ne...
Sort
View
ICASSP
2011
IEEE
12 years 8 months ago
Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?
Most HMM-based TTS systems use a hard voiced/unvoiced classification to produce a discontinuous F0 signal which is used for the generation of the source-excitation. When a mixed ...
Javier Latorre, Mark J. F. Gales, Sabine Buchholz,...
ICMCS
2006
IEEE
182views Multimedia» more  ICMCS 2006»
13 years 10 months ago
Using Semantic Features for Scene Classification: how Good do they Need to Be?
Semantic scene classification is a useful, yet challenging problem in image understanding. Most existing systems are based on low-level features, such as color or texture, and suc...
Matthew R. Boutell, Anustup Choudhury, Jiebo Luo, ...
CHI
2004
ACM
13 years 10 months ago
How do users think about ubiquitous computing?
As ubiquitous computing technology migrates into the home environment, there has been a concurrent effort to allow users to build and customize such technologies to suit their own...
Khai N. Truong, Elaine M. Huang, Molly M. Stevens,...
ML
2007
ACM
122views Machine Learning» more  ML 2007»
13 years 4 months ago
Status report: hot pickles, and how to serve them
The need for flexible forms of serialisation arises under many circumstances, e.g. for doing high-level inter-process communication or to achieve persistence. Many languages, inc...
Andreas Rossberg, Guido Tack, Leif Kornstaedt